Show HN: My LLM CLI tool can run tools now, from Python code or plugins

Post by cyanydeez » Tue, May 27, 2025, 11:36 PM UTC

furyofantares wrote: post #29

behnamoh wrote: post #2

what are the use cases for llm, the CLI tool? I keep finding tgpt or the bulletin AI features of iTerm2 sufficient for quick shell scripting. does llm have any special features that others don't? am I missing something?

I don't use llm, but I have my own "think" tool (with MUCH less support than llm, it just calls openai + some special prompt I have set) and what I use it for is when I need to call an llm from a script. Most recently I wanted a script that could produce word lists from a dictionary of 180k words given a query, like "is this an animal?" The script breaks the dictionary up into chunks of size N (asking "which of these…

Post by kristopolous » Tue, May 27, 2025, 11:37 PM UTC

simonw wrote: post #48

kristopolous wrote: post #45

It's worth noting the streaming markdown renderer I wrote just for this tool: https://github.com/day50-dev/Streamdown More background: https://github.com/simonw/llm/issues/12 (Also check out https://github.com/day50-dev/llmehelp which features a tmux tool I built on top of Simon's llm. I use it every day. Really. It's become indispensable)

Wow, that library is looking really great! I think I want a plugin hook that lets plugins take over the display of content by the tool. Just filed an issue: https://github.com/simonw/llm/issues/1112 Would love to get your feedback on it, I included a few design options but none of them feel 100% right to me yet.

Post by isaacremuant » Tue, May 27, 2025, 11:49 PM UTC

kbelder wrote: post #50

tantalor wrote: post #33

This greatly opens up the risk of footguns. The doc [1] warns about prompt injection, but I think a more likely scenario is self-inflicted harm. For instance, you give a tool access to your brokerage account to automate trading. Even without prompt injection, there's nothing preventing the bot from making stupid trades. [1] https://llm.datasette.io/en/stable/tools.html

If you hook an llm up to your brokerage account, someone is being stupid, but it ain't the bot.

Post by stavros » Wed, May 28, 2025, 12:00 AM UTC

simonw wrote: post #37

stavros wrote: post #36

Have you guys had luck with tool calls? I made a simple assistant with access to my calendar, and most models fail to call the tool to add calendar events. GPT-4.1 also regularly tries to gaslight me into believing that it added the event when it didn't call the tool! Overall, I found tool use extremely hit-and-miss, to the point where I'm sure I'm doing something wrong (I'm using the OpenAI Agents SDK, FWIW).

I get the impression that the key to getting great performance out of tool calls is having a really detailed system prompt, with a bunch of examples. Anthropic's system prompt just for their "web_search" tool is over 6,000 tokens long! https://simonwillison.net/2025/May/25/claude-4-system-prompt...

Post by kristopolous » Wed, May 28, 2025, 12:07 AM UTC

rpeden wrote: post #58

kristopolous wrote: post #45

It's worth noting the streaming markdown renderer I wrote just for this tool: https://github.com/day50-dev/Streamdown More background: https://github.com/simonw/llm/issues/12 (Also check out https://github.com/day50-dev/llmehelp which features a tmux tool I built on top of Simon's llm. I use it every day. Really. It's become indispensable)

Neat! I've written streaming Markdown renderers in a couple of languages for quickly displaying streaming LLM output. Nice to see I'm not the only one! :)

    for i in $(seq 1 6); do 
      printf "%${i}sh${i}\n\n-----\n" | tr " " "#"; 
    done | pv -bqL 30 | sd -w 30